daanzu/kaldi_ag_training

Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.

37
/ 100
Emerging

This tool helps speech recognition developers create or customize Kaldi speech models for specific applications. You provide audio recordings and their corresponding text transcripts, and it produces a specialized speech model tailored to your data. It's used by developers building custom voice control, transcription, or other speech-enabled features into their software.

No commits in the last 6 months.

Use this if you need to train a highly accurate, domain-specific speech recognition model for a Kaldi-based application, especially for use with kaldi-active-grammar.

Not ideal if you're looking for a simple, out-of-the-box speech recognition solution that doesn't require model training or if you're not comfortable working with command-line tools and Docker.

speech-recognition voice-user-interface audio-processing custom-model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

21

Forks

4

Language

Shell

License

AGPL-3.0

Last pushed

Jan 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/daanzu/kaldi_ag_training"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.